zong fan[Paper Explained] Deconstructing Denoising Diffusion Models for Self-Supervised LearningPaper Link: https://arxiv.org/abs/2401.14404Feb 21Feb 21
zong fan[Paper Explained] Take-home points of using contrastive learning on histopathological imagesContrastive learning, as a useful self-supervised learning technique, has been widely explored and utilized in the natural image field…Jun 30, 2023Jun 30, 2023
zong fanImage Augmentation Based on 3D Thin Plate Spline (TPS) Algorithm for CT DataCT is a very useful radiographical imaging method for screening lung tumors and nodules. Nowadays, deep learning-based methods are heavily…Jun 17, 2023Jun 17, 2023
zong fanAccelerate PyTorch Model With TensorRT via ONNXPyTorch is one of the most popular deep learning network frameworks due to its simplicity and flexibility with its dynamic computation…Nov 5, 20191Nov 5, 20191
zong fanDeploy ONNX models with TensorRT Inference ServingNvidia GPU is the most popular hardware to accelerate the training and inference of your deep learning models. Almost all deep learning…Nov 1, 2019Nov 1, 2019
zong fanAccelerate OpenCV DCT (Discrete Cosine Transform) in Multi-Dimensional ArrayDCT (Discrete cosine transform) is a very useful tool in signal and image processing like image compression and denoising. It is…Oct 9, 2019Oct 9, 2019
zong fanUse NVIDIA DeepStream to Accelerate H.264 Video Stream DecodingIn my previous post, I have described a method of how to use FFmpeg to do hardware acceleration of H.264 stream decoding on NVIDIA GPU…Sep 18, 20194Sep 18, 20194
zong fanUse FFmpeg to Decode H.264 Stream with NVIDIA GPU AccelerationFFmpeg is a very popular and powerful video manipulation tool that can be applied on multiple tasks including decoding, transcoding and so…Sep 8, 20193Sep 8, 20193
zong fan文章解析:FCOS: Fully Convolutional One-Stage Object Detection(Paper) (Code)Jun 18, 20191Jun 18, 20191
zong fan文章解读:EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (ICML2019)Link: (Paper) (tf code) (pytorch code)Jun 18, 2019Jun 18, 2019